Author

Won Cheng Yi Lewis

h-index 2 View on Semantic Scholar

We have 1 of 3 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... May 2026

Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs

Direct Preference Optimization (DPO) is applied to align models, constructing preference pairs in which chosen responses preserve mixed-language content while rejected responses mimic failure patterns, suggesting DPO can effectively elicit correct code-switching transcription behavior from multilingual Audio LLMs.

T. N. Quang, Won Cheng Yi Lewis, M. Pham et al. · arXiv.org · 2 citations